K-nearest neighbours (KNN) is a widely used neural network and machine learning classification algorithm. Recently, it has been used in the neural network and digital image processing fields. In this study, the KNN classifier is used to distinguish 12 different colours. These colours are black, blue, brown, forest green, green, navy, orange, pink, red, violet, white and yellow. Using colour histogram feature extraction, which is one of the image processing techniques, the features that distinguish these colours are determined. These features increase the effectiveness of the KNN classifier. The training data consist of saved frames and the test data are obtained from the video camera in real-time. The video consists of consecutive frames. The frames are 100 × 70 in size. Each frame is tested with K = 3,5,7,9 and the obtained results are recorded. In general, the best results are obtained when used K = 5.   Keywords: KNN algorithm, classifier, application, neural network, image processing, developed, colour, dataset, colour recognition.

Solar energy has gained increasing importance in today's world and become a viable primary energy source in the recent decade. Solar radiation obtained by the solar surface is highly affected by its orientation, azimuth, and tilt angles. Therefore, in this study, the performances of the fixed-axis system, one-axis, and two-axis solar tracking systems are investigated to enable maximal solar radiation in solar systems to be installed in Antalya by using climatic and latitude data provided by NASA. Furthermore, the optimal tilt angles are determined by examining the values of angles for which the total solar radiation falling on the tilted surface is maximal. The case study and measurement data investigations are conducted for the four districts of Antalya. The obtained radiation values throughout the year for one-axis and two-axis solar tracking systems are compared to an annual fixed system for evaluating the existing solar potential in Antalya province. Besides all these, solar system cost analyses including the average payback period for residential, commercial, and large-scale solar systems based on LCOE are investigated. The proposed methodology can be implemented for performance and cost analysis of the solar potential in a certain location of Türkiye and extended to any place in the world.

Rapid advancements in mobile industry have emerged new technological ideas and applications for researchers by allowing smart devices over the last decade. In recent years, the need for Indoor Position Routing (IPR) and Location-Based Advertisements (LBA) systems are increasingly common, IPR and LBA systems have been becoming very popular. Nowadays, it has become possible to create software and hardware applications for IPR and LBA in indoor environments, thanks to developments of different technologies. The development of the system should be based on low-cost technology, it should be suitable for integration and indoors operation. New options and possibilities for indoor locations are presented by the iBeacon-Bluetooth Low Energy (BLE) radio protocol. iBeacon-BLE supports portable battery-powered system that can be smoothly distributed at low cost giving it distinct advantages over Wi-Fi. Therefore, in this study, a technological infrastructure is created to solve the navigation problem in closed locations using iBeacon-BLE technology, a data monitoring information system is proposed for smart devices of currently available technology for IPR, LBA with using iBeacon-BLE. The localization of the objects based on iBeacon-BLE and their combination are determined using the measured data with the developed application. To build an IPR system for indoor environments, the available hardware, software, and network technologies are presented. The concept of the indoor monitoring system and the technologies can be used to develop the IPR system are presented. This system is made up of iBeacon-BLE sensor nodes, a smart device and a mobile application that provides IPR and LBA services by measuring the distance between Transmitter (TX) and Receiver (RX). The proposed model uses the trilateration method, it allows the mobile application to determine the exact location of the object at the micro-level size. The proposed model uses sensory data to identify and trilateration the object’s position.

No abstract